Qwen3.7 Max
Better value: GPT-5.6 Luna scores 58.1 for $0.450/M, 88% cheaper.
12 cheaper ranked models score higher: Gemini 4 Hydrogen (63.6, $3.00), GPT-6.1 Terra (63.2, $2.00), Gemini 3.5 Flash (62.4, $3.38) and 9 more.
As of 19 Nov 2026, Qwen3.7 Max by Alibaba scores 59.8 on the BenchLeader Index (top 100 of 631 ranked configurations), with its best results in instruction following (78) and weakest in agents & tools (49). API pricing: $2.50 per 1M input tokens and $7.50 per 1M output tokens ($3.75 blended at 3:1), list price on 19 Nov 2026. It streams about 150 tokens/s (Artificial Analysis). Released 19 May 2026.
Key facts (as of 19 Nov 2026)
- Qwen3.7 Max API pricing: $2.50 per 1M input tokens and $7.50 per 1M output tokens ($3.75 blended at 3:1) (list price, 19 Nov 2026).
- Qwen3.7 Max streams about 150 tokens/s (Artificial Analysis, 19 Nov 2026).
- Qwen3.7 Max was released on 19 May 2026 (Alibaba).
In detail. Qwen3.7 Max is an Alibaba proprietary reasoning model, released 19 May 2026. Its best configuration ranks #100 of 631 on the BenchLeader Index at 59.8 ±4.3, in the upper half. The ± is the point: 232 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in instruction following (78) and lowest in agents & tools (49). At $3.75 per million tokens blended it is pricier than most ranked models. Output speed of 145 tokens per second puts it in the fastest quarter, with a first answer in 14.1 s. It has been measured at 3 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 18 Nov 2026.
- Blended price
- $3.75/M
- $2.50 in · $7.50 out
- via Artificial Analysis
- Output speed
- 145 tok/s
- measured by Artificial Analysis
- First answer
- 14 s
- first token 1.18 s
- Context
- 1M
- via models.dev
- Accepts
- Text
- via models.dev, OpenRouter
- Full answer
- 31 s
- last measured 13 Nov 2026
- Cost per task
- –
- Tokens per task
- –
- Released
- 19 May 2026
- Overall index60
- Reasoning64
- Coding59
- Agents & tools49
- Maths58
- Knowledge61
- Instruction following78
- Human preference56
- Long context64
Embed this rank
More badge styles[](https://www.benchleader.com/models/qwen3-7-max)Paste it at the top of README.md, beside your other badges. The badge redraws with every data update and links back to this page.
Versions
Alibaba has shipped 4 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| Qwen3.8 Max | 3 Aug 2026 | 59.0 | #118 |
| Qwen3.7 Maxthis page | 19 May 2026 | 59.8 | #100 |
| Qwen3.6 Max | 20 Apr 2026 | 62.0 | #61 |
| Qwen3.5 Max | – | – | – |
Reasoning-effort configurations
The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Not stated” collects results from publishers that did not say which setting they used; for a reasoning model that is usually its thinking mode, but we do not assume it. Pick a setting here or at the top of the page to see its price, speed and category scores.
| Effort | Index | Rank | Speed | First answer | Chat reply cost | Categories |
|---|---|---|---|---|---|---|
| no reasoning | – | – | 145 tok/s | 14 s | $0.0033 | |
| xhigh | – | – | 145 tok/s | 14 s | $0.0033 | |
| not statedbest | 59.8 | #100 | 145 tok/s | 14 s | $0.0033 | Agents & tools 49 · Coding 59 · Human preference 56 · Instruction following 78 · Knowledge 61 · Long context 64 · Maths 58 · Reasoning 64 |
How its index has moved
8 Sep 2026 to 19 Nov 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | no reasoning | not stated | Source | Trend |
|---|---|---|---|---|
| GPQA Diamondeffort not stated | – | 90.9%#42 | Epoch AI Benchmarking Hub | |
| SimpleBencheffort not stated | – | 70.4%#26 | SimpleBench | |
| Arena Hard Promptseffort not stated | – | 1494#47 | Arena (LMArena) | |
| LiveBench 1.0 Reasoningnot in indexeffort not stated | – | 83.3%#43 | LiveBench | |
| GPQA Diamond (AA)not in indexeffort not stated | – | 92.3%#36 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in indexeffort not stated | – | 40.5%#96 | Artificial Analysis | |
| GPQA Diamond (Vals)not in indexeffort not stated | – | 90.2%#25 | Vals AI | |
| CritPtnot in indexeffort not stated | – | 13.4%#114 | Artificial Analysis | |
| Arena Expertnot in indexeffort not stated | – | 1508#36 | Arena (LMArena) | |
| Chess Puzzlesnot in indexeffort not stated | – | 27.0%#79 | Epoch AI Benchmarking Hub | |
| Mystery Game Puzzlesnot in index | 26.0%#49 | 32.0%#36 | Epoch AI Benchmarking Hub | |
| LMCAnot in indexeffort not stated | – | 44.0%#102 | Epoch AI Benchmarking Hub | |
| DTBenchnot in indexeffort not stated | – | 92.3%#76 | Epoch AI Benchmarking Hub |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| SWE-bench Verified (Epoch) | 77.3%#7 | Epoch AI Benchmarking Hub | |
| SciCode | 49.5%#129 | SciCode | |
| Arena Coding | 1524#32 | Arena (LMArena) | |
| Arena WebDev | 1516#68 | Arena (LMArena) | |
| LiveBench 1.0 Codingnot in index | 74.2%#53 | LiveBench | |
| SciCode (AA)not in index | 49.5%#130 | Artificial Analysis | |
| LiveCodeBench | 87.1%#18 | Vals AI | |
| SWE-bench (Vals)not in index | 68.8%#67 | Vals AI | |
| Code Migrationnot in index | 13.1%#60 | Vals AI | |
| Vibe Code Bench v1.1not in index | 47.7%#76 | Vals AI | |
| ALE-Benchnot in index | 1189.4#53 | Epoch AI Benchmarking Hub | |
| Terminal-Bench 4.0 (AA)not in index | 1.5%#170 | Artificial Analysis | |
| Terminal-Bench 2.1 (AA)not in index | 74.5%#66 | Artificial Analysis | |
| Startrise Frontendnot in index | 63.6%#26 | Startrise |
Agents & tools
Maths
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| FrontierMath Tiers 1–3 | 64.6%#43 | Epoch AI Benchmarking Hub | |
| FrontierMath Tier 4 | 34.1%#41 | Epoch AI Benchmarking Hub | |
| OTIS Mock AIME | 95.6%#53 | Epoch AI Benchmarking Hub | |
| ProofBench | 26.0%#47 | Vals AI | |
| LiveBench Mathematicsnot in index | 85.3%#55 | LiveBench | |
| Arena Maths | 1481#37 | Arena (LMArena) |
Knowledge
| Benchmark | xhigh | not stated | Source | Trend |
|---|---|---|---|---|
| SimpleQA Verifiedeffort not stated | – | 55.8%#27 | Epoch AI Benchmarking Hub | |
| LiveBench 1.0 Data Analysisnot in indexeffort not stated | – | 71.8%#47 | LiveBench | |
| MMLU-Proeffort not stated | – | 89.3%#12 | Vals AI | |
| LegalBencheffort not stated | – | 84.9%#28 | Vals AI | |
| CorpFineffort not stated | – | 63.7%#42 | Vals AI | |
| TaxEvaleffort not stated | – | 75.3%#19 | Vals AI | |
| Excel Modeling Benchmarknot in indexeffort not stated | – | 57.0%#43 | Vals AI | |
| MedCodenot in indexeffort not stated | – | 38.8%#68 | Vals AI | |
| MedScribenot in indexeffort not stated | – | 79.4%#62 | Vals AI | |
| DrugDiscoveryBenchnot in index | 29.3%#25 | – | Scale AI SEAL | |
| EBR-benchnot in indexeffort not stated | – | 9.5%#29 | Epoch AI Benchmarking Hub |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| LiveBench Languagenot in index | 79.7%#33 | LiveBench | |
| LiveBench Instruction Followingnot in index | 74.0%#14 | LiveBench | |
| IFBench | 80.5%#7 | Artificial Analysis | |
| Arena Instruction Followingnot in index | 1466#47 | Arena (LMArena) |
Human preference
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Text | 1474#44 | Arena (LMArena) | |
| EQ-Bench 4 | 1100#27 | EQ-Bench | |
| Arena Creative Writingnot in index | 1440#63 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1481#40 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1491#28 | Arena (LMArena) |
Long context
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-LCR v1.1 | 79.0%#120 | Artificial Analysis | |
| MLCRnot in index | 14.4%#115 | Artificial Analysis |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Epoch Capabilities Indexnot in index | 154.6#48 | Epoch AI Benchmarking Hub | |
| LiveBench 1.0not in index | 73.1%#47 | LiveBench | |
| AA Intelligence Index v4.3.2not in index | 29.5#134 | Artificial Analysis | |
| AA Progress Index v1not in index | 293.8#136 | Artificial Analysis |
API pricing: where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Alibaba Cloud Int. | 67 tok/s | 1.17 s | $1.48 | $4.42 | 1M | – |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.500 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0033 | $0.0027 | 16.1 s |
| Summarize a 30-page report | 12,000 / 600 | $0.035 | $0.017 | 18.2 s |
| Code edit | 6,000 / 1,500 | $0.026 | $0.017 | 24.4 s |
| Agentic coding session | 60,000 / 4,000 | $0.180 | $0.090 | 41.6 s |
| Structured extraction | 2,000 / 200 | $0.0065 | $0.0035 | 15.4 s |
More from Alibaba
Compare Qwen3.7 Max with…
See also
Embed or cite
Show where Qwen3.7 Max ranks on a model card or README. The badge redraws itself with every daily update, carries the data date and links back to this page.
[](https://www.benchleader.com/models/qwen3-7-max)Cite this
The ranking changes daily, so a reference carries the data date. APA style:
BenchLeader. (2026, November 19). Qwen3.7 Max on the BenchLeader Index (method v1.5) [Data set]. Retrieved November 19, 2026, from https://www.benchleader.com/models/qwen3-7-max
BibTeX:
@misc{benchleader_qwen3_7_max_20261119,
author = {{BenchLeader}},
title = {{Qwen3.7 Max on the BenchLeader Index (method v1.5)}},
year = {2026},
month = nov,
howpublished = {\url{https://www.benchleader.com/models/qwen3-7-max}},
note = {Data as of 2026-11-19}
}Every badge style, the embeddable top-10 widget and how to cite the Index
Questions people ask
- What are Qwen3.7 Max's benchmark scores?
- As of 19 Nov 2026, Qwen3.7 Max scores 59.8 ±4.3 on the BenchLeader Index, top 100, strongest in instruction following (78) and weakest in agents & tools (49). That rests on independent benchmark results only, and every score on this page links to its publisher.
- How does Qwen3.7 Max rank?
- Qwen3.7 Max is #100 of 631 ranked configurations on 19 Nov 2026 (top 100). 232 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Fable 5.2 (max effort) at 71.5.
- How much does Qwen3.7 Max cost per 1M tokens?
- As of 19 Nov 2026, Qwen3.7 Max costs $2.50 per 1M input tokens and $7.50 per 1M output tokens, $3.75 blended (three input tokens per output token).
- Is Qwen3.7 Max better than Gemini 3.8 Flash?
- As of 19 Nov 2026, Gemini 3.8 Flash (medium) and Qwen3.7 Max are neck and neck on quality (59.8 vs 59.8 on the BenchLeader Index, inside the ±6.6 margin of error), and Gemini 3.8 Flash (medium) costs 2.5× less, which makes it the better buy for most workloads. The head-to-head page has the benchmark-by-benchmark detail.
- When was Qwen3.7 Max released?
- Alibaba released Qwen3.7 Max on 19 May 2026. BenchLeader has results for it at 3 reasoning-effort settings.
Data as of 19 Nov 2026. Compare these configurations.
Cite as: BenchLeader, “Qwen3.7 Max: benchmarks, pricing, speed and rank”, data as of 19 Nov 2026, https://www.benchleader.com/models/qwen3-7-max.